Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 import torch
 import whisper
+from whisper.utils import write_vtt
 import requests
 from pytube import YouTube
 
@@ -38,9 +39,11 @@ def transcribe(audio):
     #print("Language Spoken: " + transcription.language)
     #print("Transcript: " + transcription.text)  
     #print("Translated: " + translation.text)
+    with open('sub.vtt', "w") as f:
+        write_vtt(result["segments"], file=f)
 
  
-    return result["text"]
+    return result["text"], "sub.vtt"
 
 def transcribe_upload(audio):
     return transcribe(audio)
@@ -151,9 +154,10 @@ with gr.Blocks(css = css) as demo:
 
         with gr.Row():
             transcript_output = gr.Textbox(label="Transcription in the language spoken", lines = 20)
+            transcript_file = gr.File()
     
-    transcribe_audio_yt.click(transcribe_yt, inputs = yt_input, outputs = transcript_output)
-    transcribe_audio_u.click(transcribe_upload, inputs = audio_input_u, outputs = transcript_output)   
+    transcribe_audio_yt.click(transcribe_yt, inputs = yt_input, outputs = [transcript_output, transcript_file])
+    transcribe_audio_u.click(transcribe_upload, inputs = audio_input_u, outputs = [transcript_output, transcript_file])   
     gr.HTML('''
         <div class="footer">
                     <p>Whisper Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">OpenAI</a>